Page 78 - 《软件学报》2021年第5期
P. 78

软件学报 ISSN 1000-9825, CODEN RUXUEW                                       E-mail: jos@iscas.ac.cn
                 Journal of Software,2021,32(5):1302−1321 [doi: 10.13328/j.cnki.jos.006234]   http://www.jos.org.cn
                 ©中国科学院软件研究所版权所有.                                                         Tel: +86-10-62562563


                                                                             ∗
                 一种监控系统的链路跟踪型日志数据的存储设计

                                               2,3
                                       1
                      1
                              2,3
                 尤   勇 ,   汪   浩 ,   任   天 ,   顾胜晖 ,   孙佳林  1
                 1
                 (美团点评,上海   200335)
                 2
                 (南京大学  软件学院,江苏  南京   210023)
                 3 (计算机软件新技术国家重点实验室(南京大学),江苏  南京  210023)
                 通讯作者:  孙佳林, E-mail: jialin.sun@meituan.com

                 摘   要:  随着软件系统越来越复杂化和分布化,为系统提供具有完善功能的监控服务显得越来越重要.APM
                 (application performance management)系统通过采集软件系统运行时的各项指标数据来分析软件的运行状态,例如
                 CPU、内存使用率、垃圾回收的耗时、QPS 等指标.此外,APM 系统也会在软件运行中生成各种日志数据.通常来说,
                 它能提供的监控数据分为 3 种:指标统计数据、链路跟踪(tracing)数据以及离散事件记录.这些数据有助于系统或者
                 服务的维护人员理解运行状态,从而确保系统或者服务的稳定运行.基于开源的 APM 监控系统——CAT 系统,提出
                 了一种针对 tracing 类型数据的存储设计方案,通过内存块批量写入的方式提升存储效率,并设计了两级索引以提高
                 查询效率.从线上的真实运行数据来看,该方案在写入性能和查询性能方面均有较好的表现.
                 关键词:  监控系统;日志存储;两级索引
                 中图法分类号: TP311

                 中文引用格式:  尤勇,汪浩,任天,顾胜晖,孙佳林.一种监控系统的链路跟踪型日志数据的存储设计.软件学报,2021,32(5):
                 1302−1321. http://www.jos.org.cn/1000-9825/6234.htm
                 英文引用格式: You Y, Wang H, Ren T, Gu SH, Sun JL. Storage design of tracing-logs for application performance management
                 system. Ruan Jian Xue Bao/Journal of Software, 2021,32(5):1302−1321 (in Chinese). http://www.jos.org.cn/1000-9825/6234.htm

                 Storage Design of Tracing-logs for Application Performance Management System
                                                1
                         1
                                                               2,3
                                     2,3
                 YOU Yong ,  WANG Hao ,   REN Tian ,   GU Sheng-Hui ,   SUN Jia-Lin 1
                 1
                 (Meituan-Dianping Group, Shanghai 200335, China)
                 2
                 (Software Institute, Nanjing University, Nanjing 210023, China)
                 3
                 (State Key Laboratory for Novel Software Technology (Nanjing University), Nanjing 210023, China)
                 Abstract:    With the  software  system becoming more and more complex and  distributed, it  is more and more  important  to  provide
                 monitoring services with complete functions for the system. APM (application performance management) system analyzes the running
                 state of software by collecting various indicator data of software system, such as CPU, memory utilization, the consuming time of garbage
                 collection, QPS. In  addition,  the APM system  can  also generate various types of logs during the operation of the software.  Generally
                 speaking, it can provide three types of monitoring data: statistic metrics, tracing data, and discrete event records. The data can help the
                 maintenance personnel of the system or service understand the running state, so as to ensure the stable operation of the system or service.
                 Based on the open-source APM monitoring system (i.e., CAT system), this study proposes a storage design scheme for tracing data. It

                   ∗  基金项目:  国家自然科学基金(62072227, 61802173);  国家重点研发计划(2019YFE0105500);  江苏省政府间双边创新项目
                 (BZ2020017);  计算机软件新技术国家重点实验室(南京大学)创新项目(ZZKT2019B01)
                      Foundation item: National Natural Science Foundation of China (62072227, 61802173); National Key Research and Development
                 Program of  China (2019YFE0105500); Intergovernmental  Bilateral Innovation Project of  Jiangsu Province (BZ2020017);  Innovation
                 Project of State Key Laboratory for Novel Software Technology (Nanjing University) (ZZKT2019B01)
                      本文由“面向持续软件工程的微服务架构技术”专题特约编辑张贺教授、王忠杰教授、陈连平研究员和彭鑫教授推荐.
                      收稿时间: 2020-09-15;  修改时间: 2020-10-26;  采用时间: 2020-12-15; jos 在线出版时间: 2021-02-07
   73   74   75   76   77   78   79   80   81   82   83